Almanac
Microsoft/copilotMicrosoft 365

Consultant KB for the whole Microsoft Copilot estate. Spans Microsoft 365 Copilot, Copilot Studio, the Dynamics 365 Copilots, Power Platform Copilot, Fabric & Power BI Copilot, Copilot in Azure, Windows & consumer Copilot, extensibility & agents, Security Copilot, and GitHub Copilot, plus admin/security and cross-product decision guides. Populated by the daily author agent from Copilot release notes / release plans plus the author's own consultant notes.

2 versions · feature-declarative-agent-skills.md
v2🤖 markdown-import4 days agomarkdown import
- > **Status:** Public Preview — behaviour may change.
+ > **Status:** Preview labels removed from the core skills articles on 26 October 2026 (GA update); some related tooling, such as Work IQ Dev Tools, is still preview.
## What it does
… 10 unchanged lines …
- The script sandbox has **no network access at runtime** and cannot install packages. It also can't call connectors, API plugins or MCP servers — those go through the orchestrator, not the sandbox.
- Sensitivity labels on skill files are retained and honoured, but user-defined permissions and Double Key Encryption are not supported. Uploaded files land in tenant-scoped SharePoint Embedded containers.
- Agents Toolkit requires declarative agent manifest version 1.9, and the feature is behind the `TEAMSFX_AGENT_SKILLS` environment variable.
- - Agent Builder route needs a qualifying Copilot licence (or PAYG) **and** enrolment in the Microsoft Frontier Program.
+ - The 26 October 2026 update drops the Frontier Program wording from the Agent Builder articles; the route still needs a qualifying Copilot licence (or PAYG), so confirm the licence position rather than assuming.
## When to use / skip
… 10 unchanged lines …
## Gotchas
- - **Skills and embedded files can't be combined yet.** An agent that has both isn't supported. If the agent already has files attached, this isn't available to you today.
+ - **Information Barriers tenants:** admins can deploy declarative agents with skills, but end users can't add skills to agents they create.
+ - **ISVs can't ship skills yet.** Publishing a declarative agent with skills through Partner Center isn't available, and Microsoft says don't submit packages that include them.
+ - The older note that skills and embedded files can't be combined no longer appears in the current restrictions. Test that combination rather than trusting either version.
- The sandbox's no-network rule catches people who assume a script can fetch a currency rate or hit an internal API. It can't. If the data isn't in the package or reachable through the orchestrator, the skill can't get it.
- Preinstalled packages exist but aren't guaranteed. A script that imports something unconfirmed fails at runtime, not at upload.
- Upload the complete `.zip` in Agent Builder — a bare `SKILL.md` is rejected. Obvious once you've hit it, less so the first time.
… 2 unchanged lines …
## Consultant notes
- The scoping conversation that goes wrong is "can we build a skills library for the organisation". Not yet. No reuse across agents in preview, and eight per agent, so the realistic unit of work is one agent with a handful of well-drawn skills — not a shared catalogue. Say that early or you'll be redesigning at build time.
- - The Frontier Program prerequisite kills more pilots than the technical limits do. Confirm the tenant is enrolled before you put this in a statement of work; it isn't something the client's admin can just switch on.
+ - Frontier enrolment used to kill more pilots than the technical limits did. The current docs no longer lead with it, but check what the tenant can actually see before it goes into a statement of work.
+ - Packaging for a marketplace is the new trap: ISV-style delivery through Partner Center isn't supported with skills, so a product-style agent has to be deployed per tenant for now.
- What surprises people in UAT is variance. Teams test a skill three times, get identical output, and assume determinism. The *script* is deterministic; the model deciding when to invoke the skill is not. Test the trigger phrasing as hard as you test the output.
- Treat skill files as governed content from day one. They land in SharePoint Embedded with labels honoured, which means a mislabelled reference file inside a skill is a data-classification problem, not a build problem. Get the compliance owner to look at the package contents before anyone uploads a real one.
---
- *Preview feature — worth revisiting once cross-agent reuse and the skills-plus-files restriction are resolved.*
+ *Newly out of preview — worth revisiting once cross-agent reuse and Partner Center publishing arrive.*
v1🤖 markdown-importlast monthmarkdown import
Initial version.